CN110070862B

CN110070862B - Method and system for automatic guidance based on ontology in dialogue system

Info

Publication number: CN110070862B
Application number: CN201910047833.6A
Authority: CN
Inventors: J.森; P.杰因; D.萨哈; A.米塔尔
Original assignee: International Business Machines Corp
Current assignee: International Business Machines Corp
Priority date: 2018-01-19
Filing date: 2019-01-18
Publication date: 2023-06-16
Anticipated expiration: 2039-01-18
Also published as: CN110070862A; US10839160B2; US20190228068A1

Abstract

The present application relates generally to information technology, and more particularly, to dialog framework technology. The present disclosure provides methods, systems, and computer program products for booting a state-based dialog system. A computer-implemented method includes determining parameters of a state automaton by dividing an ontology graph into subgraphs and dividing a knowledge graph into subgraphs, wherein the ontology graph and the knowledge graph are based on user questions and domain knowledge related to the user questions; generating a structured query for each sub-graph; determining intent of a dialog related to at least one user question by translating each generated structured query into a corresponding natural language query; creating one or more dialog states for each determined dialog intention; creating one or more connection dialog states between the created dialog state pairs; and generating an automaton dialog framework associated with the user question based on the created dialog state and the created connection dialog state.

Description

Method and system for automatic guidance based on ontology in dialogue system

Technical Field

The present application relates generally to information technology, and more particularly, to dialog framework technology.

Background

Existing dialog frameworks are typically based on a generic framework with a core having a state-based automaton model. Any terminal application attempting to use such a dialog framework requires custom fill state automaton parameters to instantiate a dialog framework appropriate for the application. However, custom filling automaton parameters requires manual intervention and often creates a major bottleneck in instantiating the dialog framework of the terminal application.

Disclosure of Invention

In one embodiment of the present invention, techniques for ontology-based automatic guidance of a state-based dialog system are provided. An exemplary computer-implemented method may include determining one or more parameters of a state automaton for use by one or more automatic dialog exchange programs by partitioning (i) at least one ontology graph into a plurality of subgraphs, and (ii) at least one knowledge graph into a plurality of subgraphs, wherein each of (i) the at least one ontology graph and (ii) the at least one knowledge graph is based on at least one user problem and domain knowledge related to the at least one user problem, and wherein each state representation in the state automaton includes structured actions of at least one of queries and commands. The method further includes generating a structured query for each of the plurality of subgraphs, and determining one or more intents of a dialog related to the at least one user problem by translating each of the generated structured queries into a corresponding natural language query. In addition, the method includes creating one or more dialog states for each of the determined dialog intents, creating one or more connection dialog states between the created dialog state pairs; and generating an automaton dialog framework associated with the at least one user question based on (i) the created dialog state and (ii) the created connection dialog state.

In another embodiment of the invention, an exemplary computer-implemented method may include: based on the analysis of the ontology graphs and knowledge graphs related to a particular terminal application, a plurality of states of a state automaton dialog framework are identified as valid interpretation graphs on the ontology graphs, wherein each of the plurality of states represents a structured action; determining one or more conversion rules between related ones of the identified states, wherein each conversion rule captures how a state automaton dialog framework evolves from a first state to a second state; assigning a natural language paragraph (natural language passages) to the one or more conversion rules; and designing a state automaton dialog framework for a particular end application based on (i) the plurality of states, (ii) the one or more conversion rules, and (iii) the assigned natural language paragraphs.

Another embodiment of the invention or elements thereof may be implemented in the form of a computer program product containing computer readable instructions which, when implemented, cause a computer to perform a plurality of method steps as described herein. Furthermore, another embodiment of the invention or an element thereof may be implemented in the form of a system comprising a memory and at least one processor coupled to the memory and configured to perform the mentioned method steps. Furthermore, another embodiment of the invention or an element thereof may be implemented in the form of an apparatus or an element thereof for performing the method steps described herein; the apparatus may comprise hardware modules or a combination of hardware and software modules, where the software modules are stored in a computer-readable storage medium (or a plurality of such media).

These and other objects, features and advantages of the present invention will become apparent from the following detailed description of illustrative embodiments thereof, which is to be read in connection with the accompanying drawings.

Drawings

FIG. 1 is a schematic diagram illustrating a system architecture according to an exemplary embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating ontology partitioning according to an exemplary embodiment of the present invention;

FIG. 3 is a schematic diagram illustrating creation of a query class in accordance with an exemplary embodiment of the present invention;

FIG. 4 is a schematic diagram illustrating the creation of an ontology-dependent parameterized query in accordance with an exemplary embodiment of the present invention;

FIG. 5 is a schematic diagram illustrating a intent to create in accordance with an exemplary embodiment of the present invention;

FIG. 6 is a diagram illustrating a dialog state according to an exemplary embodiment of the present invention;

fig. 7 is a diagram illustrating a transition state according to an exemplary embodiment of the present invention;

FIG. 8 is a flow chart illustrating a technique according to an embodiment of the invention;

FIG. 9 is a system diagram of an exemplary computer system upon which at least one embodiment of the invention may be implemented;

FIG. 10 depicts a cloud computing environment according to an embodiment of the invention; and

FIG. 11 depicts an abstract model layer, according to an embodiment of the invention.

Detailed Description

As described herein, one embodiment of the present invention includes an ontology-based automatic guidance of a state-based dialog system. At least one embodiment of the invention may include utilizing domain knowledge from an ontology and one or more knowledge graphs to design a complete state automaton. In such a state automaton, each state may represent a structured action (such as a query or command) on an element in the ontology. Furthermore, in such a state automaton, the transition between two states captures how the dialog flow evolves from motion to action. Further, such a state automaton may enable a chat robot (i.e., an automated dialog exchange program) to understand natural language actions (e.g., queries or commands) and take appropriate actions by converting the natural language actions into structured actions.

Accordingly, one or more embodiments of the present invention include automatically filling state automaton parameter slots to design and instantiate a dialog framework for a related-art ontology-based terminal application. Such embodiments include automatically creating an ontology and knowledge graph based on analysis of user questions, user intent, and domain knowledge related to the user questions. Further, such embodiments may include extracting parameters for the state automaton by dividing the ontology and knowledge graph into sub-graphs based on data collected from one or more external sources. In at least one embodiment of the invention, the ontology partitioning process may include implementing functional partitioning of the ontology to determine the number of relationships to traverse from a particular evidence set of a partial-type query by considering boundaries between individual domain functions.

Further, such embodiments may also include automatically mapping ontology-based domain knowledge to state automaton parameters, and populating state parameters for redesigning and instantiating the automaton dialog framework.

Bridging chat robotic automata using ontologies, as described herein, may include the use of the following terms and elements. Each interpretation graph in the ontology is referred to herein as a "state" in the chat robot automaton. Thus, each state Identifier (ID) uniquely identifies an interpretation graph in the ontology, and each transition edge between interpretations is also a state that captures non-sequential statements (non-sequential utterance, NSU) and/or co-references that flow between interpretations. In addition, the "input context" of the state may be expressed as: (previous state id+fill parameter value), while the "output context" of the state may be represented as (current state id+fill parameter value).

In addition, the "output action" may refer to a backend action identified by the interpretation of the state and ultimately performed. The backend actions may be any content specific to the application. An "entity" may refer to an ontology concept, attribute, etc., and a "sample question" may include a natural language question and/or a generated non-sentence utterance that may cause an automaton to transition from one state to another. As also detailed herein, "parameters" may include desired parameters and optional parameters. The required parameters may include, for example, a single conceptual state, a conceptual entity. Optional parameters may include, for example, a union of data attributes for all concepts in an interpretation graph for a given state.

At least one embodiment of the invention may also include enumeration states and transition edges. Such an embodiment may include dividing an ontology graph into a plurality of subgraphs, o= { P ₁ ,P ₂ ,…P _n -wherein each sub-graph P _i Unique semantic relationships are captured in the ontology. One or more embodiments of the present invention may further include setting states: set (Set)<States>S= { }. In such an embodiment, for each partition P _i All possible combinations of concepts in the partition are generated (C _i ∈P _i ). For each generated concept combination CC _i Such embodiments may include determining a connection concept combination CC _i Is defined, is a set of possible interpretation trees. For each determined tree IT _CCi Such embodiments may further include creating a state SIT if the state creates a valid interpretation map _CCi . In addition, a state SIT can be generated _CCi Is set equal to { data attribute (C) _i ) } to make C _i ∈CC _i . Thus, with such an embodiment, s=s+sit _CCi 。

The invention is thatMay further include determining a transition edge. For example, within each partition, SIT for each pair of states _CCi ,SIT _CCj E S, if

Then add the transition edge as SIT _CCi →SIT _CCj . As another example, across partitions, SIT for each pair of states _CCi ,SIT _CCj ∈S，/>

Concept C causes C εSIT _CCi ∩SIT _CCj Or C.epsilon.SIT _CCi And Parent (c) εSIT _CCj ) Then take the transition edge as SIT _CCi →SIT _CCj And (5) adding.

Furthermore, at least one embodiment of the invention may include implementing an algorithm for filling in the internal details of the state. For example, for a pair of states (S _i ,S _j ) Each edge in between, such an embodiment may include taking the output context as context_out _i (i.e. State ID S _i +fill parameter value) is added to S _i And is used as context_in _j (i.e., context_in _j U (State ID S) _i +fill parameter value)) to S _j Is defined, is a context of input. Further, for each state S _i If S _i Is a single conceptual state, one or more embodiments of the invention may include adding "conceptual entities" as required parameters; otherwise, this embodiment may include adding "the sum of data attributes of all concepts in the explanatory diagram of this state" as an optional parameter.

At least one embodiment of the present invention further includes implementing an algorithm for generating example questions for chat robot state transitions. For example, generating a problem for self-cycling transitions in states may include the following. For each state S _i For all possible S _i Parameter P of (2) _i The random sample N parameter sets may be represented as P _is (i.e. random (P) _i N)). For P _is Each parameter set p, Q of (a) _i ＝Q _i U (generate one sample problem with p).

Furthermore, at least one embodiment of the invention may include implementing an algorithm for filling in the internal details of the state. For example, for a pair of states (S _i ,S _j ) Each edge in between, such an embodiment may include taking the output context as context_out _i (i.e., state ID S _i +fill parameter value) is added to S _i And is used as context_in _j (i.e., context_in _j U (State ID S) _i +fill parameter value) is added to S _j Is defined, is a context of input. Further, for each state S _i If S _i Is a single conceptual state, one or more embodiments of the invention may include adding "conceptual entities" as required parameters; otherwise, this embodiment may include adding "merging of data attributes of all concepts in the explanatory diagram of this state" as an optional parameter.

At least one embodiment of the present invention further includes implementing an algorithm for generating sample questions for chat robot state transitions. For example, generating a problem for self-cycling transitions in states may include the following. For each state S _i For S _i All possible parameter sets P of (2) _i The random sample N parameter set may be represented as P _is (i.e. random (P) _i N)). For P _is Each parameter set p, Q of (a) _i ＝Q _i U (using p to generate the sample problem).

Further, one or more embodiments of the invention may include generating questions for transitions between states. For each transition between states (S _i ->S _j ) And for all possible set parameters P _ij As S _j But at S _i In the absence of a random sample, the N parameter sets may be represented as P _ijs (i.e. random (P) _ij N)). For P _ijs Each parameter set p, Q of (a) _ij ＝Q _ij U，Using p can generate a sample problem.

At least one embodiment of the present invention may further include identifying and/or generating a start state. In such an embodiment, the automaton may begin in a state of an interpretation graph corresponding to the first query submitted to the chat bot. Similarly, at least one embodiment of the present invention may additionally include identifying and/or generating a stopped state. In such an embodiment, the automaton may have a single stopped state, which may be reached from multiple states. For example, for a target drive system, each possible target state may reach a stopped state after a certain duration without further problems. In addition, for non-target driven systems, each state in the automaton may reach a stopped state after processing certain inputs (e.g., an "end dialog" phrase) and/or after a period of time has elapsed without further problems. In addition, a set of questions indicating that a target state has been reached or that an "end session" phrase has been processed may be taken as input from the user of the target terminal application being developed.

FIG. 1 is a schematic diagram illustrating a system architecture according to an embodiment of the invention. For illustration purposes, fig. 1 depicts an ontology 102 and Knowledge Graph (KG) 104, which are used to guide system 106 to perform

steps

108, 110, and 112. Specifically, step 108 includes marking the state as a valid interpreted graph on the partition's ontology. One or more embodiments of the invention may also include partitioning the ontology 102. Further, step 110 includes validating possible conversion rules between associated states, and step 112 includes assigning Natural Language (NL) sentences to the conversion rules for intent resolution.

As also shown in FIG. 1, the output of the guidance system 106 (e.g., including the specified NL sentence) may include a dialog state automaton 114 from which chat robots 118 are created. For example, one or more embodiments of the invention can include implementing a chat robot build framework to employ chat robot specifications (e.g., conversational state automata) and create a chat robot. Chat bot 118 provides a structured action to query and/or command processor 120, which returns a response to chat bot 118. In addition, the terminal application 116 transmits natural language actions (e.g., queries and/or commands) to the chat robot 118, which returns responses to the terminal application 116 based on information obtained from the dialog state automaton 114 and the query and/or command processor 120.

Fig. 2 is a schematic diagram illustrating ontology partitioning according to an exemplary embodiment of the present invention. For example, FIG. 2 depicts dividing the body into a first portion 202 and a second portion 204. As detailed herein, the number of explanatory diagrams may be large in combination given one ontology. Thus, one or more embodiments of the invention may include enumerating states only within a partition, without having new states across partitions (including transition edges only). Such embodiments may include narrowing the state space to a manageable limited set.

FIG. 3 is a schematic diagram illustrating the creation of a query class in accordance with an exemplary embodiment of the present invention. For example, FIG. 3 depicts a collection of queries 302, where the queries are described in a language (SQL-) such as a structured query language, which may specify structured queries. As shown in fig. 3, c1..c … =concept, and c1_p1=any attribute P1 of C1. In addition, c1_intaggr_p1 is an attribute P1 of C1, for which an integer is polymerizable, and path_c1_c2=a PATH between C1 and C2 in the ontology. In addition, c1_int_p1_val is the value of c1_int_p1. Further, in one or more embodiments of the invention, such query classes may be manually specified.

FIG. 4 is a schematic diagram of creating ontology-based parameterized queries 402 and 404 according to an exemplary embodiment of the present invention. At least one embodiment of the invention, as shown in FIG. 4, includes a creation entity. Such created entities may include value entities and/or schema element entities. With respect to value entities, one or more embodiments may include looking up in an ontology attributes (e.g., company name, chief Executive Officer (CEO) name, etc.) that may be referenced in a query. Such an embodiment may then include obtaining values for the attributes and creating an entity for each value. With respect to schema element entities, for all concepts in an ontology and its attributes, one or more embodiments of the invention may include entities that create synonyms that contain those entities.

Fig. 5 is a diagram of a creation intention according to an exemplary embodiment of the present invention. By way of illustration, FIG. 5 depicts a step 502 that includes generating a specific action from a parameterized action (using values from an entity). Step 502 may also include instantiating with one or more values so that the intent classifier can accurately classify the action. 504 includes generating one or more natural language queries corresponding to each specific action, where the NL queries are examples of intent. For example, step 504 may be performed using a different component that parses the query and replaces the query with a natural language phrase.

Fig. 6 is a diagram illustrating a dialogue state according to an exemplary embodiment of the present invention. By way of illustration, FIG. 6 depicts a "show all lenders to me" dialog state 602, a "show all loans to me protocol" dialog state 604, a "show all borrowers to me" dialog state 606, a "show all lenders to me" dialog state 608, a "show all loans by borrower" dialog state 610, and a "show loan by borrower A to me" dialog state 612. In addition, in one or more embodiments of the invention, the response of each dialog state is a parameterized ontology-dependent query. Further, within each dialog state, ontology concepts from which states are created may be presented and/or included.

Fig. 7 is a diagram of a transition state according to an exemplary embodiment of the present invention. By way of illustration, fig. 7 depicts exemplary transition states 702, 704, 706, 708, 710, and 712. In connection with the example embodiment depicted in fig. 7, consider the following runtime flow. The user submits a query, which is then matched to one of the dialog states by matching the query to the closest intent. In addition, relevant query parameters will be automatically populated and/or generated. For example, suppose that the user has queried "show me the chief executive officer of the airline. ". Further, assume that an entity industry name (name) exists for "airline". In this way, the dialog system may map the query to a dialog state with an intent instance of "show me CEO of IT company". Such a system embodiment may also find the response by appropriate parameterization. Such a query may then be retrieved and executed by the command processor, and a corresponding response may be generated and displayed to the user.

Fig. 8 is a flow chart of a technique according to an embodiment of the invention. Step 802 includes dividing (i) at least one ontology graph into a plurality of subgraphs; and (ii) dividing at least one knowledge graph into a plurality of subgraphs, determining one or more parameters of a state automaton used by one or more automated dialog exchange programs, wherein (i) the at least one ontology graph and (ii) each of the at least one knowledge graph are based on domain knowledge of and about at least one user problem, and wherein each state in the state automaton represents a structured action comprising at least one query and command.

Determining the one or more parameters may include creating one or more ontology-independent structured action classes and creating one or more ontology-dependent parameterized actions based on the one or more ontology-independent structured action classes. Further, one or more embodiments of the invention may include generating an action intent for each ontology-dependent parameterized action, and generating one or more specific actions based on the one or more ontology-dependent parameterized actions. Further, at least one embodiment of the invention may include deriving an identification of one or more entities based on one or more ontology-dependent parameterized actions and generating one or more specific actions using values from the one or more entities. One or more embodiments of the invention may also include generating one or more natural language queries corresponding to each particular action.

Step 804 includes generating a structured query for each of the plurality of subgraphs. Step 806 includes determining one or more intents for a dialog about the at least one user question by translating each generated structured query into a corresponding natural language query.

Step 808 includes creating one or more dialog states for each determined dialog intention. Creating one or more dialog states may include creating one or more action dialog states for each generated action intent and representing differences between the two action dialog states using one or more natural language actions.

Step 810 includes creating one or more connection dialog states between the created dialog state pairs. Step 812 includes generating an automaton dialog framework associated with the at least one user question based on (i) the created dialog state and (ii) the created connection dialog state. Additionally, one or more embodiments of the present invention may include creating a non-sequential utterance intention related to a difference, creating a transition dialog state associated with two action dialog states, creating a dialog flow including the two action dialog states and the transition dialog state, and assigning the created non-sequential utterance intention to the transition dialog state.

Further, additional embodiments of the present invention include identifying a plurality of states of the state automaton dialog framework as valid interpretation graphs on the ontology graph, wherein each of the plurality of states represents one structured action, based on an analysis of the ontology graph and knowledge graph associated with a particular terminal application. This embodiment may also include determining one or more transition rules between the identified relevant states, wherein each transition rule captures how the state automaton dialog framework evolves from the first state to the second state. In addition, this embodiment may include assigning natural language paragraphs to one or more conversion rules based on (i) a plurality of states, (ii) one or more conversions, and (iii) assigned natural language paragraphs, and designing a state automaton dialog framework for a particular end application. This embodiment may also include having one or more automated dialog exchange programs (referred to herein as chat robots) perform one or more actions by converting one or more natural language paragraphs into one or more structured actions.

The technique depicted in fig. 8 may also include providing a system, where the system includes different software modules, each of which is contained on a tangible computer-readable recordable storage medium, as described herein. For example, all of the modules (or any subset thereof) may be on the same medium, or each module may be on a different medium. A module may include any or all of the components shown in the figures and/or described herein. In one embodiment of the invention, the modules may run, for example, on a hardware processor. The method steps may then be performed using different software modules of the system, as described above, executing on a hardware processor. Furthermore, the computer program product may comprise a tangible computer readable recordable storage medium having code adapted to be executed to implement at least one of the method steps described herein, the code comprising providing a system having different software modules.

Additionally, the techniques depicted in FIG. 8 may be implemented by a computer program product that may include computer usable program code stored in a computer readable storage medium in a data processing system, and wherein the computer usable program code is downloaded from a remote data processing system over a network. Furthermore, in an embodiment of the invention, a computer program product may include computer usable program code stored in a computer readable storage medium in a server data processing system, and wherein the computer usable program code is downloaded over a network to a remote data processing system for use in a computer readable storage medium having the remote system.

Embodiments of the invention or elements thereof may be implemented in the form of an apparatus including a memory and at least one processor coupled to the memory and configured to perform exemplary method steps.

In addition, embodiments of the invention may utilize software running on a computer or workstation. With reference to FIG. 9, such an implementation may employ, for example, a processor 902, memory 904, and an input/output interface formed, for example, by a display 906 and a keyboard 908. The term "processor" as used herein is intended to include any processing device, such as, for example, one that includes a CPU (central processing unit) and/or other forms of processing circuitry. Furthermore, the term "processor" may refer to more than one individual processor. The term "memory" is intended to include memory associated with a processor or CPU, such as RAM (random access memory), ROM (read only memory), a fixed memory device (e.g., hard drive), a removable storage device (e.g., diskette), flash memory, etc. In addition, the phrase "input/output interface" as used herein is intended to include, for example, mechanisms for inputting data to a processing unit (e.g., a mouse), as well as mechanisms for providing results associated with a processing unit (e.g., a printer). The processor 902, memory 904, and input/output interfaces such as a display 906 and a keyboard 908 may be interconnected as part of a data processing system 912, for example via a bus 910. Suitable interconnections, such as through bus 910, may also be provided to a network interface 914, such as a network card, which may be provided to interface with a computer network, and to a media interface 916, such as a disk or CD-ROM drive, which may be provided to interface with media 918.

Thus, as described herein, computer software comprising instructions or code for performing the methodologies of the invention may be stored in an associated memory device (e.g., ROM, fixed or removable memory) and, when ready to be implemented, loaded in part or in whole (e.g., into RAM) and implemented by a CPU. Such software may include, but is not limited to, firmware, resident software, microcode, etc.

A data processing system suitable for storing and/or executing program code will include at least one processor 902 coupled directly or indirectly to memory elements 904 through a system bus 910. The memory elements can include local memory employed during actual implementation of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during implementation.

Input/output or I/O devices (including but not limited to keyboards 908, displays 906, pointing devices, etc.) can be coupled to the system either directly (e.g., through bus 910) or through intervening I/O controllers (omitted for clarity).

Network adapters such as network interface 914 may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.

As used herein, including the claims, a "server" includes a physical data processing system (e.g., system 912 as shown in fig. 9) running a server program. It should be understood that such physical servers may or may not include a display and keyboard.

The present invention may be a system, method and/or computer program product at any level of technical details possible. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to perform embodiments of the present invention.

A computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium would include the following: portable computer diskette, hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable reader-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disc read-only memory (CD-ROM), digital Versatile Disc (DVD), memory stick, floppy disk, mechanical coding device such as a punch card or protrusion structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, should not be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated through waveguides or other transmission media (e.g., passing light pulses) fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded to the corresponding computing/processing devices from a computer readable storage medium or an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.

Computer readable program instructions for performing the operations of the present invention may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or source or object code written in one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and a procedural programming language such as the "C" programming language or any combination of similar programming languages. The computer readable program instructions may be executed as a stand alone software package, entirely on the user's computer, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, to perform embodiments of the present invention, electronic circuitry, including, for example, programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), may be personalized by executing computer-readable program instructions using state information of the computer-readable program instructions.

Embodiments of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which implement the functions/acts specified in the flowchart and/or block diagram block or blocks, are implemented by the processor of the computer or other programmable data processing apparatus. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus and/or other devices to function in a particular manner, such that the computer-readable storage medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that any of the methods described herein may include the additional step of providing a system comprising different software modules embodied on a computer-readable storage medium; a module may include, for example, any or all of the components detailed herein. The method steps may then be performed using different software modules and/or sub-modules of the system executing on the hardware processor 902, as described above. Furthermore, the computer program product may comprise a computer readable storage medium having code adapted to be implemented to perform at least one of the method steps described herein, the method steps comprising providing a system having different software modules.

In any event, it is to be understood that the components illustrated herein can be implemented in various forms of hardware, software, or combinations thereof, e.g., application Specific Integrated Circuits (ASICS), functional circuitry, a suitable programmable digital computer with associated memory, etc. Other embodiments of the assembly of the present invention will be apparent to those of ordinary skill in the relevant art in view of the teachings of the present invention provided herein.

In addition, it is to be appreciated in advance that implementation of the teachings described herein are not limited to a particular computing environment. Rather, embodiments of the invention can be implemented in connection with any type of computing environment, now known or later developed.

Cloud computing is a service delivery model for convenient, on-demand network access to a shared pool of configurable computing resources. Configurable computing resources are resources that can be quickly deployed and released with minimal administrative costs or minimal interaction with service providers, such as networks, network bandwidth, servers, processes, memory, storage, applications, virtual machines, and services. Such cloud patterns may include at least five features, at least three service models, and at least four deployment models.

The characteristics are as follows:

on-demand self-service: a consumer of the cloud can unilaterally automatically deploy computing capabilities such as server time and network storage on demand without human interaction with the service provider.

Wide network access: computing power may be obtained over a network through standard mechanisms that facilitate the use of the cloud by heterogeneous thin client platforms or thick client platforms (e.g., mobile phones, laptops, personal digital assistants PDAs).

And (3) a resource pool: the provider's computing resources are grouped into resource pools and served to multiple consumers through a multi-tenant (multi-tenant) model, where different physical and virtual resources are dynamically allocated and reallocated as needed. Typically, the consumer is not able to control or even know the exact location of the provided resources, but can specify locations (e.g., countries, states, or data centers) at a higher level of abstraction, and therefore have location independence.

Rapid elasticity: the computing power can be deployed quickly, flexibly (sometimes automatically) to achieve a quick expansion, and can be released quickly to shrink quickly. The available computing power for deployment tends to appear infinite to consumers and can be accessed at any time and in any number of ways.

Measurable services: cloud systems automatically control and optimize resource utility by leveraging metering capabilities of some degree of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both the service provider and consumer.

The service model is as follows:

software as a service (SaaS): the capability provided to the consumer is to use an application that the provider runs on the cloud infrastructure. Applications may be accessed from various client devices through a thin client interface such as a web browser (e.g., web-based email). With the exception of limited user-specific application configuration settings, consumers do not manage nor control the underlying cloud infrastructure including networks, servers, operating systems, storage, or even individual application capabilities, etc.

Platform as a service (PaaS): the capability provided to the consumer is to deploy consumer created or obtained applications on the cloud infrastructure, which are created using programming languages and tools supported by the provider. The consumer does not manage nor control the underlying cloud infrastructure, including the network, server, operating system, or storage, but has control over the applications it deploys, and possibly also over the application hosting environment configuration.

Infrastructure as a service (IaaS): the capability provided to the consumer is the processing, storage, networking, and other underlying computing resources in which the consumer can deploy and run any software, including operating systems and applications. The consumer does not manage nor control the underlying cloud infrastructure, but has control over the operating system, storage, and applications deployed thereof, and may have limited control over selected network components (e.g., host firewalls).

The deployment model is as follows:

private cloud: the cloud infrastructure alone runs for some organization. The cloud infrastructure may be managed by the organization or a third party and may exist inside or outside the organization.

Community cloud: the cloud infrastructure is shared by several organizations and supports specific communities of common interest (e.g., mission tasks, security requirements, policies, and compliance considerations). The community cloud may be managed by multiple organizations or third parties within a community and may exist inside or outside the community.

Public cloud: the cloud infrastructure provides public or large industry groups and is owned by an organization selling cloud services.

Mixing cloud: the cloud infrastructure consists of two or more clouds of deployment models (private, community, or public) that remain unique entities, but are bound together by standardized or proprietary technologies that enable data and applications to migrate (e.g., cloud bursting traffic sharing technology for load balancing between clouds).

Cloud computing environments are service-oriented, with features focused on stateless, low-coupling, modular, and semantic interoperability. At the heart of cloud computing is an infrastructure that includes a network of interconnected nodes.

Referring now to FIG. 10, an exemplary cloud computing environment 50 is depicted. As shown, cloud computing environment 50 includes one or more cloud computing nodes 10 with which local computing devices used by cloud computing consumers, such as Personal Digital Assistants (PDAs) or mobile telephones 54A, desktop computers 54B, notebook computers 54C, and/or automobile computer systems 54N, may communicate. Cloud computing nodes 10 may communicate with each other. Cloud computing nodes 10 may be physically or virtually grouped (not shown) in one or more networks including, but not limited to, private, community, public, or hybrid clouds as described above, or a combination thereof. In this way, cloud consumers can request infrastructure as a service (IaaS), platform as a service (PaaS), and/or software as a service (SaaS) provided by the cloud computing environment 50 without maintaining resources on the local computing device. It should be appreciated that the various computing devices 54A-N shown in fig. 10 are merely illustrative, and that cloud computing node 10 and cloud computing environment 50 may communicate with any type of computing device (e.g., using a web browser) over any type of network and/or network-addressable connection.

Referring now to FIG. 11, a set of functional abstraction layers provided by cloud computing environment 50 (FIG. 11) is shown. It should be understood at the outset that the components, layers, and functions shown in FIG. 11 are illustrative only, and embodiments of the present invention are not limited in this regard. As shown in fig. 11, the following layers and corresponding functions are provided:

the hardware and software layer 60 includes hardware and software components. Examples of hardware components include: host 61, RISC (reduced instruction set computer) architecture based server 62, server 63, blade server 64, storage 65, and network components 66. In some embodiments, the software components include web application server software 67 and database software 68. The virtual layer 70 provides an abstraction layer that may provide examples of the following virtual entities: virtual servers, virtual storage, virtual networks (including virtual private networks), virtual applications and operating systems, and virtual clients.

In one example, management layer 80 may provide the following functionality: resource supply function: providing dynamic acquisition of computing resources and other resources for performing tasks in a cloud computing environment; metering and pricing functions: cost tracking of resource usage within a cloud computing environment and billing and invoicing therefor are provided. In one example, the resource may include an application software license. Safety function: identity authentication is provided for cloud consumers and tasks, and protection is provided for data and other resources. User portal function: providing consumers and system administrators with access to the cloud computing environment. Service level management function: allocation and management of cloud computing resources is provided to meet the requisite level of service. Service Level Agreement (SLA) planning and fulfillment functions: scheduling and provisioning is provided for future demands on cloud computing resources according to SLA predictions.

In accordance with one or more embodiments of the invention, the workload layer 90 provides an example of functionality that may utilize a cloud computing environment. Examples of workloads and functions that may be provided from this layer include: mapping and navigation 91, software development and lifecycle management 92, virtual classroom education distribution 93, data analysis processing 94, transaction processing 95, and ontology-based automated guidance 96.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of other features, steps, operations, elements, components, and/or groups thereof.

At least one embodiment of the present invention may provide benefits such as automatically filling state automaton parameter slots to instantiate a dialog framework for an end application based on an ontology of domain knowledge.

The foregoing description of embodiments of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A computer-implemented method, the method comprising the steps of:

determining one or more parameters of a state automaton for use by one or more automated dialog exchange programs by partitioning each of at least one ontology graph into a plurality of subgraphs, and partitioning each of at least one knowledge graph into a plurality of subgraphs, wherein each of the at least one ontology graph and the at least one knowledge graph is based on at least one user problem and domain knowledge related to the at least one user problem, and wherein each state in the state automaton represents a structured action comprising at least one of a query and a command;

Generating a structured query for each of the plurality of subgraphs;

determining one or more intents of a dialog related to the at least one user question by translating each generated structured query into a corresponding natural language query;

creating one or more dialog states for each determined dialog intention;

creating one or more connection dialog states between the created dialog state pairs; and

generating an automaton dialog framework associated with the at least one user question based on the created dialog state and the created connection dialog state;

wherein the steps are performed by at least one computing device.

2. The computer-implemented method of claim 1, wherein determining one or more parameters of a state automaton comprises creating one or more structured action classes that are independent of an ontology.

3. The computer-implemented method of claim 2, wherein the determining one or more parameters of the state automaton comprises creating one or more ontology-dependent parameterized actions based on the one or more ontology-independent structured action classes.

4. The computer-implemented method of claim 3, wherein the determining one or more parameters of the state automaton comprises generating an action intent for each of the ontology-dependent parameterized actions.

5. The computer-implemented method of claim 3, wherein the determining one or more parameters of the state automaton comprises generating one or more specific actions based on the one or more ontology-dependent parameterized actions.

6. The computer-implemented method of claim 3, wherein the determining one or more parameters of the state automaton comprises deriving an identification of one or more entities.

7. The computer-implemented method of claim 6, wherein the determining one or more parameters of the state automaton comprises generating one or more specific actions using values from the one or more entities based on the one or more ontology-dependent parameterized actions.

8. The computer-implemented method of claim 5, wherein determining one or more parameters of the state automaton comprises generating one or more natural language queries corresponding to each of the specific actions.

9. The computer-implemented method of claim 4, wherein said creating one or more dialog states comprises creating one or more action dialog states for each of said generated action intents.

10. The computer-implemented method of claim 9, wherein the creating one or more dialog states includes representing a difference between two action dialog states using one or more natural language actions.

11. The computer-implemented method of claim 10, comprising:

a non-sequential utterance intention related to the discrepancy is created.

12. The computer-implemented method of claim 11, wherein the creating one or more dialog states comprises creating a transition dialog state associated with the two action dialog states.

13. The computer-implemented method of claim 12, wherein the generating an automaton dialog framework comprises creating a dialog flow comprising the two action dialog states and the transition dialog state.

14. The computer-implemented method of claim 12, wherein the generating an automaton dialog framework comprises assigning the created non-sequential utterance intention to the transition dialog state.

15. A computer readable storage medium having stored therein program instructions executable by a computing device to cause the computing device to perform the method of any of claims 1-14.

16. A computer system, comprising:

a memory; and

at least one processor operably coupled to the memory and configured to perform the method of any of claims 1-14.

17. A computer system comprising modules for performing the steps of the method of any one of claims 1-14, respectively.